Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1922 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1782707 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.4179. Min Act: -0.0000

Data Index: 686055 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1403877 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2708. Min Act: -0.0000

Data Index: 807612 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2738. Min Act: -0.0000

Data Index: 336126 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.3008. Min Act: -0.0000

Data Index: 624903 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2848. Min Act: -0.0000

Data Index: 654547 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1490357 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1544310 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2464. Min Act: -0.0000

Data Index: 906732 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2961. Min Act: -0.0000

Data Index: 732963 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1894. Min Act: -0.0000

Data Index: 973318 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1301647 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2475. Min Act: -0.0000

Data Index: 227013 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2411. Min Act: -0.0000

Data Index: 100530 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2298. Min Act: -0.0000

Data Index: 728745 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1291227 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1328806 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1547426 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2508. Min Act: -0.0000

Data Index: 126726 (The Pile)

Max Activating Token Index: 416